Follow Discord
Sweep 29 Sep 2026 · 18:10Z Build v2.1.285 506 read Stable v2.1.280 Latest v2.1.285 Next v2.1.285 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.280entry #290

Claude Code v2.1.280 ·

Remote Control messaging about claude.ai projects gated behind a new flag

Text about starting Remote Control sessions from claude.ai projects or the mobile app is now gated by its own flag, tengu_bridge_rc_projects_hint.

Group of 3 Nothing to try yet In Development
JSON All of v2.1.280
Nothing to try yetTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Remote ControlArea: what it touches
In DevelopmentKind: in v2.1.280,
In DevelopmentSection of the release

What

  • The claude remote-control help/description text can now mention that claude.ai projects can ask Claude to work in the current directory, controlled by a gate that defaults to true in the in-bundle fallback.
  • The onboarding prompt shown before enabling Remote Control can now mention opening the Code tab in the Claude mobile app or asking Claude to work in the folder from claude.ai, shown only when this "projects hint" gate is on (otherwise a shorter fallback text is shown).
  • This "projects hint" behavior, previously gated by the flag tengu_cuddly_willow, now has its own dedicated flag, tengu_bridge_rc_projects_hint; tengu_cuddly_willow itself is now reused by a new helper that adds a check for settled flags before evaluating.

Why

This separates the projects-hint messaging from the older, differently-purposed tengu_cuddly_willow flag so it can be controlled independently.

Read from
Names in the bundleclaude.ai/code
Feature flag
tengu_bridge_rc_projects_hint Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.280: on

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.280. It isn't a statement about your account. What a flag value here can and cannot tell you

Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on Platforms and integrations touched a line naming claude.ai/code after this was published. | [Remote Control](/docs/en/remote-control) | Drive a running session from [claude.ai/code](https://claude.ai/code) or the Claude mobile app | Your machine (CLI, Desktop, or VS Code) | Run [`claude remote-control` or `/remote-control`](/do… platforms see the edit
Confirmed since Anthropic's documentation has since written up claude.ai/code, on Claude Code changelog. * \[VSCode] Fixed a claude.ai/code session opening empty or with only part of its conversation, with no error, when the server failed to return its history, part of it failed to load, or a network sign-in page answered in its place; it now… changelog see the edit
How sure we are
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up claude.ai/code, on Claude Code changelog.
The name it cites is new in this buildNew in this build: tengu_bridge_rc_projects_hint

See this entry in the whole of v2.1.280 →

Feedback